Skill UI

Apply Martin Fowler-inspired refactoring rules to improve existing code structure while preserving observable behavior. Covers code smells, small safe refactoring steps, test-backed cleanup, and separating refactoring from feature changes.

This skill applies Refactoring.Guru-inspired rules for diagnosing code smells and selecting appropriate refactoring techniques. It helps preserve behavior while avoiding uncontrolled redesign. Before making design or code decisions, read the mini rules first. Use the full guide only as a deeper reference when needed. It ensures targeted cleanup without over-engineering.

Apply Michael T. Nygard-inspired production reliability rules when designing failure handling, timeouts, retries, circuit breakers, observability, or deployment behavior.

Combines welfare readouts such as weight loss, temperature, clinical scores and biomarkers into a single RELSA severity score per animal per day, with kernel-density attention/danger zones and ARIMA-based forecasting of upcoming humane endpoints for 3Rs refinement reporting.

Summarizes the current workspace and reports fixture status, giving a quick overview of the project state for developers and teams.

This skill helps maintainers verify reported bugs in the mcp-toolbox project. It involves analyzing issue reports, checking versions and configurations, and attempting local reproduction to determine if the bug is real, fixed, or misconfigured. The process requires citing specific evidence like file paths and commit SHAs to support verdicts such as confirmed, already-fixed, or client-side issues. It ensures efficient bug triage without unnecessary infrastructure setup.

Sweeps googleapis/mcp-toolbox for issues and PRs with no real activity in N days, classifies each silence as the author's, maintainer's, or nobody's, and drafts nudge or close comments for maintainer review only.

Generate and cut videos against a distilled style pack: plan takes, generate with fal, apply measured LUT grading, edit at cadence, weave footage, composite overlays, mint 3D props, and verify results numerically.

Measure reference videos into reusable style packs: 3D LUT grades, cut rhythm, stills, overlay plates, and specs for generative models. Use to capture looks, build repeatable grades, and match pacing.

Apply pragmatic programming rules inspired by Hunt and Thomas to improve engineering judgment, feedback loops, DRY knowledge, orthogonality, automation, and adaptability. Use this skill for design and code decisions requiring pragmatic engineering tradeoffs.

Interviews an unshaped idea into a verdict and a design document with literal decisions for tlc-plan. Use for problem exploration, discovery, feasibility checks, and deciding whether to build before planning implementation.

This skill extracts a checklist from planned work, builds the implementation, and verifies every check with an independent verifier. It is used when the user requests to extract a checklist, build a ticket, or implement a spec. It ensures rigorous testing and proof-based assertions, preventing self-reporting of completion. It involves extracting checks, building the code, and proving each one independently to guarantee quality.